Patching Deep Neural Networks for Nonstationary Environments
| Autor: | Sebastian Kauschke, David Hermann Lehmann, Johannes Fürnkranz |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Concept drift
Artificial neural network business.industry Computer science Pattern recognition 02 engineering and technology ComputingMethodologies_PATTERNRECOGNITION 020204 information systems 0202 electrical engineering electronic engineering information engineering Deep neural networks 020201 artificial intelligence & image processing Artificial intelligence business Transfer of learning Classifier (UML) |
| Zdroj: | IJCNN |
| DOI: | 10.1109/ijcnn.2019.8852222 |
| Popis: | In this work we present neural network patching, an approach for adapting deep neural network models to nonstationary environments. Instead of creating or updating a network to accommodate concept drift, neural network patching leverages the inner layers of a previously trained network as well as its output to learn a patch that enhances the classification. It learns (i) a predictor that estimates whether the original network will misclassify an instance, and (ii) a patching network that fixes the misclassification. Neural network patching is based on the idea that the original network can still classify a majority of instances well, and that the inner feature representations encoded in the deep network aid the classifier to cope with unseen or changed inputs. We evaluated this technique on several datasets, comparing it to similar methods. Our finding is that neural network patching is adapting quickly to concept shifts, while also maintaining long-term learning capabilities similar to more complex methods that update the whole network. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|